Double Critic Deep Reinforcement Learning for Mapless 3D Navigation of Unmanned Aerial Vehicles.
Ricardo Bedin GrandoJunior Costa de JesusVictor Augusto KichAlisson Henrique KollingPaulo Lilles Drews Jr.Published in: CoRR (2021)
Keyphrases
- unmanned aerial vehicles
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- function approximation
- temporal difference
- path planning
- search and rescue
- autonomous vehicles
- policy gradient
- dynamic environments
- obstacle avoidance
- state space
- autonomous systems
- model free
- multi agent
- optimal control
- optimal policy
- control algorithm
- approximate dynamic programming
- human operators
- function approximators
- collision avoidance
- action selection
- markov decision processes
- dynamic programming
- reinforcement learning methods
- ground truth
- machine learning